Triple

T22589854
Position Surface form Disambiguated ID Type / Status
Subject Valour FC E564913 entity
Predicate hasRival P1375 FINISHED
Object Cavalry FC NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Cavalry FC | Statement: [Valour FC, hasRival, Cavalry FC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cavalry FC
Context triple: [Valour FC, hasRival, Cavalry FC]
  • A. Cavalry FC chosen
    Cavalry FC is a professional soccer club based in the Calgary area that competes in the Canadian Premier League.
  • B. Reign FC
    Reign FC is a professional women's soccer club based in the Seattle area that competes in the National Women's Soccer League.
  • C. Rio Ave F.C.
    Rio Ave F.C. is a Portuguese professional football club based in Vila do Conde, known for competing in the country's top-tier league and developing notable talent.
  • D. Eastside FC
    Eastside FC is a youth soccer club based in the Seattle area known for developing high-level players, including future U.S. international Jordan Morris.
  • E. Central United FC
    Central United FC is a New Zealand football club known for competing in regional and national competitions and for featuring players such as Aaran Lines.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1615f63788190acf776b313f0794a completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:48 p.m.